Messages in this thread | | | Date | Wed, 29 Jul 2015 15:01:48 +0200 | From | Frederic Weisbecker <> | Subject | Re: [PATCH 07/10] sched: Migrate sched to use new tick dependency mask model |
| |
On Fri, Jul 24, 2015 at 12:56:42PM -0400, Chris Metcalf wrote: > On 07/23/2015 12:42 PM, Frederic Weisbecker wrote: > >+static inline void sched_update_tick_dependency(struct rq *rq) > >+{ > >+ int cpu; > >+ > >+ if (!tick_nohz_full_enabled()) > >+ return; > >+ > >+ cpu = cpu_of(rq); > >+ > >+ if (!tick_nohz_full_cpu(rq->cpu)) > >+ return; > >+ > >+ if (sched_can_stop_tick(rq)) > >+ tick_nohz_clear_tick_dependency_cpu(TICK_SCHED_BIT, cpu); > >+ else > >+ tick_nohz_set_tick_dependency_cpu(TICK_SCHED_BIT, cpu); > >+} > > Is it worth asserting that the rq is locked at this point? Presumably that's > a requirement so that the cpu can't change out from under you.
Indeed it has become a requirement here. I'll add a check.
Thanks.
| |